Azure-Samples/azure-search-openai-demo

18.1

Adjusted Score

18.1

Raw Score

100%

Time Factor

2026-07-13

Last Push

7.7K

Stars

Python

Language

58.4K

Lines of Code

462

Files

739

Pattern Hits

2026-07-14

Scan Date

0.03

HC Hit Rate

What These Metrics Mean

Adjusted Score: Primary synthetic code indicator. Raw score normalised per 1,000 lines of code and multiplied by the temporal discount factor. This is the definitive comparative metric — use it to rank repositories by AI authorship density.
Raw Score: The unmodified sum of all severity-weighted, context-multiplied pattern match scores before temporal discounting. Reflects the absolute signal strength independent of when the repository was last active.
Time Factor: The temporal discount multiplier (0–100%) applied to the raw score. Repositories last updated before ChatGPT's launch (Nov 2022) receive a 5% factor. Full signal is only assigned to repositories active in the post-adoption era (Jan 2024+).
Pattern Hits: Total count of individual pattern matches across all files and categories. A high hit count with a low score may indicate a very large codebase with isolated AI snippets; a low count with a high score indicates dense, concentrated AI signatures.
HC Hit Rate: High+Critical pattern hits per file, averaged across the repository. This orthogonal signal catches repositories where a few files are densely packed with high-severity AI tells — a strong indicator even when the normalised score appears moderate due to codebase size.
Lines of Code / Files: Total lines and files analysed. The scanner examines 94 file extensions. These denominators are used to normalise the score, enabling fair comparison between repositories of vastly different sizes.

Score History

Longitudinal tracking requires multiple scan runs. Once this repository is re-scanned after new commits land, this chart will visualise how the synthetic code signal evolves over time — enabling you to detect whether AI authorship is growing, stabilising, or being actively corrected by human engineers.

No multi-scan history yet — run the scanner again to build trend data.

Severity Breakdown

Classifies detected patterns by their diagnostic confidence and structural impact. CRITICAL patterns (coefficient 10) represent definitive synthetic signatures — hallucinated imports, explicit LLM attribution metadata — virtually never produced by human authors. HIGH (5) indicates strong structural tells such as cross-file repetition or cross-linguistic idioms. MEDIUM (2) covers recognisable conversational padding and AI-specific vocabulary. LOW (1) captures subtle indicators like tautological comments and generic boilerplate that require density to carry independent signal.

CRITICAL 11HIGH 4MEDIUM 103LOW 621

Directory Score Breakdown

This horizontal bar chart decomposes the repository's raw synthetic code score by top-level directory, allowing you to pinpoint precisely which modules or components carry the highest AI authorship density. Directories with disproportionately high scores relative to their size warrant targeted manual review: concentrated AI signatures often trace back to mass-generated configuration layers, auto-ported test suites, LLM-scaffolded boilerplate classes, or entire subsystems authored under heavy copilot assistance. Use this view to prioritise your human code-review effort.

Pattern Findings

The scanner identified 739 distinct pattern matches across 19 syntactic categories. Each entry below represents a discrete location in the source code where the engine recorded a statistically significant AI authorship indicator. Expand any category row to inspect the individual file paths, line numbers, code snippets, and the lexical context (CODE, COMMENT, or STRING) in which each match was detected.

Reading the findings table: The Severity column indicates the diagnostic confidence level (CRITICAL / HIGH / MEDIUM / LOW). The Context column identifies whether the match occurred inside executable code, an inline comment, or a string literal — comment-context matches receive a ×1.5 weight because LLMs systematically over-annotate. The ⚡ bolt icon marks clustered matches: three or more patterns within a 10-line window, each receiving an additional ×1.5 density multiplier as dense clusters constitute far stronger evidence of synthetic authorship than isolated hits.

Hyper-Verbose Identifiers478 hits · 458 pts

Severity	File	Line	Snippet	Context
LOW	evals/generate_ground_truth.py	55	def generate_ground_truth_ragas(num_questions=200, num_search_documents=None, kg_file=None):	CODE
LOW	evals/eval_compare.py	124	def paired_permutation_p_value(deltas: list[float], iterations: int, seed: int) -> float:	CODE
LOW	evals/evaltools/eval/evaluate_metrics/base_metric.py	19	def get_aggregate_stats_for_numeric_rating(cls, df, rating_column_name):	CODE
LOW	evals/tests/test_review_utils.py	29	def test_summarize_results_single_run(tmp_path):	CODE
LOW	evals/tests/test_review_utils.py	51	def test_summarize_results_drops_unshared_metrics(tmp_path):	CODE
LOW	evals/tests/test_review_utils.py	81	def test_summarize_results_missing_stat_uses_placeholder(tmp_path):	CODE
LOW	evals/tests/test_review_utils.py	116	def test_summarize_results_drops_metric_without_recognized_stat(tmp_path):	CODE
LOW	evals/tests/test_review_utils.py	141	def test_diff_directories_no_filter(tmp_path):	CODE
LOW	evals/tests/test_review_utils.py	152	def test_diff_directories_changed_filters_equal(tmp_path):	CODE
LOW	evals/tests/test_review_utils.py	175	def test_diff_directories_changed_uses_isclose(tmp_path):	CODE
LOW	evals/tests/test_review_utils.py	185	def test_diff_directories_changed_skips_missing_and_none(tmp_path):	CODE
LOW	evals/tests/test_review_utils.py	216	def test_diff_markdown_escapes_html(tmp_path):	CODE
LOW	evals/tests/test_review_utils.py	242	def test_diff_markdown_includes_metric_rows(tmp_path):	CODE
LOW	evals/tests/test_review_utils.py	265	def test_diff_markdown_handles_non_numeric_metric_in_later_run(tmp_path):	CODE
LOW	evals/tests/test_review_utils.py	290	def test_summary_markdown_highlights_run(tmp_path):	CODE
LOW	evals/tests/test_review_utils.py	311	def test_summary_markdown_unknown_highlight_run_raises(tmp_path):	CODE
LOW	evals/tests/test_evaluate.py	37	def test_send_question_to_target_valid(monkeypatch):	CODE
LOW⚡	evals/tests/test_evaluate.py	49	def test_send_question_to_target_missing_error_stored(monkeypatch):	CODE
LOW⚡	evals/tests/test_evaluate.py	59	def test_send_question_to_target_missing_all_raises(monkeypatch):	CODE
LOW⚡	evals/tests/test_evaluate.py	67	def test_send_question_to_target_missing_context_raises(monkeypatch):	CODE
LOW⚡	evals/tests/test_evaluate.py	75	def test_send_question_to_target_invalid_json_raises(monkeypatch):	CODE
LOW	evals/tests/test_evaluate.py	87	def test_send_question_to_target_dict_context(monkeypatch):	CODE
LOW	evals/tests/test_evaluate.py	98	def test_send_question_to_target_http_error_raises(monkeypatch):	CODE
LOW	evals/tests/test_evaluate.py	111	def test_send_question_to_target_http_error_stored(monkeypatch):	CODE
LOW	evals/tests/test_evaluate_metrics.py	60	def test_citations_matched_with_page_anchors():	CODE
LOW	evals/tests/test_evaluate_metrics.py	68	def test_citations_matched_none():	CODE
LOW	evals/tests/test_evaluate_metrics.py	87	def test_latency_all_requests_failed():	CODE
LOW	evals/tests/test_evaluate_metrics.py	109	def test_builtin_groundedness():	CODE
LOW	evals/tests/test_evaluate_metrics.py	133	def test_builtin_metrics_use_supplied_credential(monkeypatch):	CODE
LOW	evals/tests/test_evaluate_metrics.py	166	def test_builtin_rating_missing_values():	CODE
LOW	…omponents/SupportingContent/SupportingContentParser.ts	8	export function parseSupportingContentItem(item: string): ParsedSupportingContentItem {	CODE
LOW	app/backend/setup_cloud_ingestion.py	29	async def setup_cloud_ingestion_strategy(	CODE
LOW	app/backend/prepdocs.py	37	async def check_search_service_connectivity(search_service: str) -> bool:	CODE
LOW	app/backend/approaches/approach.py	897	async def compute_multimodal_embedding(self, q: str):	CODE
LOW	app/backend/approaches/approach.py	903	def get_system_prompt_variables(self, override_prompt: Optional[str]) -> dict[str, str]:	CODE
LOW	app/backend/approaches/approach.py	926	def get_lowest_reasoning_effort(self, model: str) -> ReasoningEffort:	CODE
LOW	app/backend/approaches/approach.py	932	def get_reasoning_effort_options(model: str) -> list[str]:	CODE
LOW	app/backend/approaches/approach.py	985	def format_thought_step_for_chatcompletion(	CODE
LOW	app/backend/approaches/chatreadretrieveread.py	102	def extract_followup_questions(self, content: Optional[str]):	CODE
LOW	app/backend/approaches/chatreadretrieveread.py	424	async def run_agentic_retrieval_approach(	CODE
LOW	app/backend/approaches/chatreadretrieveread.py	482	def _select_knowledgebase_client(	CODE
LOW	app/backend/core/authentication.py	77	def get_auth_setup_for_client(self) -> dict[str, Any]:	CODE
LOW	app/backend/core/authentication.py	142	async def get_auth_claims_if_enabled(self, headers: dict) -> dict[str, Any]:	CODE
LOW	app/backend/prepdocslib/textprocessor.py	14	def combine_text_with_figures(page: "Page") -> None:	CODE
LOW	app/backend/prepdocslib/strategy.py	44	def create_search_index_client(self) -> SearchIndexClient:	CODE
LOW	app/backend/prepdocslib/strategy.py	47	def create_search_indexer_client(self) -> SearchIndexerClient:	CODE
LOW	app/backend/prepdocslib/servicesetup.py	141	def setup_image_embeddings_service(	CODE
LOW	app/backend/prepdocslib/servicesetup.py	318	def select_processor_for_filename(file_name: str, file_processors: dict[str, FileProcessor]) -> FileProcessor:	CODE
LOW	app/backend/prepdocslib/embeddings.py	196	async def create_embedding_for_image(self, image_bytes: bytes) -> list[float]:	CODE
LOW	app/backend/prepdocslib/embeddings.py	214	async def create_embedding_for_text(self, q: str):	CODE
LOW	app/backend/prepdocslib/blobmanager.py	35	def sourcepage_from_file_page(cls, filename, page=0) -> str:	CODE
LOW	app/backend/prepdocslib/blobmanager.py	208	def _get_image_directory_path(self, document_filename: str, user_oid: str, page_num: Optional[int] = None) -> str:	CODE
LOW	app/backend/prepdocslib/blobmanager.py	418	def get_managedidentity_connectionstring(self):	CODE
LOW	app/backend/prepdocslib/figureprocessor.py	84	def mark_content_understanding_ready(self) -> None:	CODE
LOW	app/backend/prepdocslib/textsplitter.py	292	def _should_cross_page_overlap(self, prev: Chunk, nxt: Chunk) -> bool:	CODE
LOW	app/backend/chat_history/cosmosdb.py	81	async def get_chat_history_sessions(auth_claims: dict[str, Any]):	CODE
LOW	app/backend/chat_history/cosmosdb.py	174	async def delete_chat_history_session(auth_claims: dict[str, Any], session_id: str):	CODE
LOW	app/functions/text_processor/function_app.py	48	def configure_global_settings():	CODE
LOW	app/functions/document_extractor/function_app.py	48	def configure_global_settings():	CODE
LOW	app/functions/document_extractor/function_app.py	343	def build_document_components(	CODE
418 more matches not shown…

Modern AI Meta-Vocabulary45 hits · 135 pts

Severity	File	Line	Snippet	Context
MEDIUM	README.md	20	# RAG chat app with Azure OpenAI and Azure AI Search (Python)	COMMENT
MEDIUM	AGENTS.md	85	## Adding a new setting to "Developer Settings" in RAG app	COMMENT
MEDIUM	app/frontend/src/components/AnalysisPanel/AgentPlan.tsx	174	// Extract effort from first agentic reasoning step	COMMENT
MEDIUM	app/frontend/src/pages/chat/Chat.tsx	380	// Preserve streaming preference when agentic retrieval forces streaming off.	COMMENT
MEDIUM	app/backend/approaches/approach.py	68	ref_id: Optional[str] = None # Reference id from agentic retrieval (if applicable)	CODE
MEDIUM	app/backend/approaches/approach.py	441	# STEP 1: Invoke agentic retrieval	COMMENT
MEDIUM	app/backend/approaches/chatreadretrieveread.py	160	# Handle non-streaming Response (e.g. when agentic retrieval already provided an answer)	COMMENT
MEDIUM	app/backend/approaches/chatreadretrieveread.py	244	# If agentic retrieval already provided an answer, skip final call to LLM	COMMENT
MEDIUM	tests/e2e.py	700	# Verify that agentic retrieval option is visible	COMMENT
MEDIUM	tests/e2e.py	758	# Non-streaming agentic snapshot whose query_plan carries the execution steps	COMMENT
MEDIUM	tests/test_searchmanager.py	1065	# Provide a SearchInfo configured for agentic retrieval and image search	COMMENT
MEDIUM	tests/test_searchmanager.py	1144	# Provide a SearchInfo configured for agentic retrieval	COMMENT
MEDIUM	docs/reasoning.md	1	# RAG chat: Using reasoning models	COMMENT
MEDIUM	docs/textsplitter.md	1	# RAG Chat: Text splitting algorithm overview	COMMENT
MEDIUM	docs/login_and_acl.md	20	# RAG chat: Setting up optional login and document level access control	COMMENT
MEDIUM	docs/safety_evaluation.md	1	# Evaluating RAG answer safety	COMMENT
MEDIUM	docs/architecture.md	1	# RAG Chat: Application Architecture	COMMENT
MEDIUM	docs/deploy_lowcost.md	1	# RAG chat: Deploying with minimal costs	COMMENT
MEDIUM	docs/azd.md	1	# RAG chat: Deploying with the Azure Developer CLI	COMMENT
MEDIUM	docs/customization.md	1	# RAG chat: Customizing the chat app	COMMENT
MEDIUM⚡	docs/agentic_retrieval.md	1	# RAG chat: Using agentic retrieval	COMMENT
MEDIUM⚡	docs/agentic_retrieval.md	1	# RAG chat: Using agentic retrieval	COMMENT
MEDIUM⚡	docs/agentic_retrieval.md	3	This repository includes an optional feature that uses [agentic retrieval from Azure AI Search](https://learn.microsoft.	CODE
MEDIUM	docs/agentic_retrieval.md	27	You can only change it to one of the [supported models](https://learn.microsoft.com/azure/search/search-agentic-retri	CODE
MEDIUM	docs/agentic_retrieval.md	53	> ⚠️ The Microsoft Data Protection Addendum doesn't apply to data sent to Web Knowledge Source. [Learn more in the We	CODE
MEDIUM	docs/deploy_troubleshooting.md	1	# RAG chat: Troubleshooting deployment	COMMENT
MEDIUM	docs/deploy_freetrial.md	1	# RAG chat: Deploying with a free trial account	COMMENT
MEDIUM	docs/deploy_private.md	20	# RAG chat: Deploying with private access	COMMENT
MEDIUM	docs/azure_app_service.md	1	# RAG chat: Deploying on Azure App Service	COMMENT
MEDIUM	docs/appservice.md	1	# RAG chat: Debugging the app on App Service	COMMENT
MEDIUM	docs/localdev.md	1	# RAG chat: Local development of chat app	COMMENT
MEDIUM	docs/deploy_features.md	1	# RAG chat: Enabling optional features	COMMENT
MEDIUM	docs/deploy_features.md	105	## Using agentic retrieval	COMMENT
MEDIUM	docs/azure_container_apps.md	1	# RAG chat: Deploying on Azure Container Apps	COMMENT
MEDIUM	docs/other_samples.md	1	# RAG chat: Alternative RAG chat samples	COMMENT
MEDIUM	docs/sharing_environments.md	1	# RAG chat: Sharing deployment environments	COMMENT
MEDIUM	docs/http_protocol.md	1	# RAG Chat: HTTP Protocol	COMMENT
MEDIUM	docs/http_protocol.md	85	## HTTP responses from RAG chat app endpoints	COMMENT
MEDIUM	docs/monitoring.md	1	# RAG chat: Monitoring with Application Insights	COMMENT
MEDIUM	docs/deploy_existing.md	2	# RAG chat: Deploying with existing Azure resources	COMMENT
MEDIUM	docs/productionizing.md	1	# RAG chat: Productionizing the app	COMMENT
MEDIUM	docs/multimodal.md	1	# RAG chat: Support for multimodal documents	COMMENT
MEDIUM	docs/data_ingestion.md	1	# RAG chat: Data ingestion	COMMENT
MEDIUM	docs/evaluation.md	1	# Evaluating the RAG answer quality	COMMENT
MEDIUM	docs/evaluation.md	118	## Evaluate multimodal RAG answers	COMMENT

Self-Referential Comments38 hits · 130 pts

Severity	File	Line	Snippet	Context
MEDIUM	app/backend/setup_cloud_ingestion.py	119	# Create a list file strategy for uploading files from the data folder	COMMENT
MEDIUM	app/backend/setup_cloud_ingestion.py	122	# Create the cloud ingestion strategy	COMMENT
MEDIUM	app/backend/app.py	184	# Create a BytesIO object from the bytes	COMMENT
MEDIUM	app/backend/prepdocslib/csvparser.py	31	# Create a CSV reader from the text content	COMMENT
MEDIUM	app/backend/prepdocslib/integratedvectorizerstrategy.py	182	# Create an indexer	COMMENT
MEDIUM	app/backend/prepdocslib/searchmanager.py	173	# Create the AI Vision vectorizer for image embeddings	COMMENT
MEDIUM	app/functions/text_processor/function_app.py	237	# Create a lightweight File wrapper required by process_text	COMMENT
MEDIUM	tests/test_mediadescriber.py	176	# Create a mock OpenAI response	COMMENT
MEDIUM	tests/test_mediadescriber.py	207	# Create the describer with the mock client	COMMENT
MEDIUM	tests/test_mediadescriber.py	277	# Create the describer	COMMENT
MEDIUM⚡	tests/test_prepdocslib_filestrategy.py	26	# Create a mock file	COMMENT
MEDIUM⚡	tests/test_prepdocslib_filestrategy.py	30	# Create a mock processor	COMMENT
MEDIUM⚡	tests/test_prepdocslib_filestrategy.py	34	# Create a page with an image	COMMENT
MEDIUM⚡	tests/test_embeddings.py	46	# Create a text that exceeds the 8100 token limit	COMMENT
MEDIUM⚡	tests/test_prepdocs.py	167	# Create the ImageEmbeddings instance	COMMENT
MEDIUM⚡	tests/test_authenticationhelper.py	49	# Create a payload with necessary claims	COMMENT
MEDIUM⚡	tests/test_authenticationhelper.py	66	# Create a header	COMMENT
MEDIUM⚡	tests/test_authenticationhelper.py	69	# Create a mock private key (for signing)	COMMENT
MEDIUM⚡	tests/test_authenticationhelper.py	72	# Create the JWT	COMMENT
MEDIUM	tests/test_upload.py	18	# Create a mock class for DataLakeDirectoryClient that includes the _client attribute	COMMENT
MEDIUM	tests/test_upload.py	93	# Create a mock class for DataLakeDirectoryClient that includes the _client attribute	COMMENT
MEDIUM⚡	tests/test_chatapproach.py	272	# Create a mock for the ImageEmbeddings.create_embedding_for_text method	COMMENT
MEDIUM⚡	tests/test_chatapproach.py	279	# Create a mock ImageEmbeddings instance and set it on the chat_approach	COMMENT
MEDIUM	tests/test_chatapproach.py	297	# Create a chat approach without an image_embeddings_client	COMMENT
MEDIUM	tests/test_cosmosdb_migration.py	110	# Create the migrator with our mocks	COMMENT
MEDIUM	tests/test_cosmosdb_migration.py	180	# Create a mock for the CosmosDBMigrator	COMMENT
MEDIUM	tests/test_blob_manager.py	186	# Create a blob manager with an image container	COMMENT
MEDIUM	tests/test_blob_manager.py	197	# Create a test file and image bytes	COMMENT
MEDIUM	tests/test_blob_manager.py	200	# Create a simple 1x1 transparent PNG image	COMMENT
MEDIUM	tests/test_searchmanager.py	200	# Create a simple mock embeddings object with just the properties we need for index creation	COMMENT
MEDIUM	tests/test_searchmanager.py	918	# Create a SearchInfo with an Azure Vision endpoint	COMMENT
MEDIUM	tests/test_searchmanager.py	926	# Create a SearchManager with search_images=True	COMMENT
MEDIUM	tests/test_searchmanager.py	968	# Create a SearchManager with search_images=True but no Azure Vision endpoint	COMMENT
MEDIUM	tests/test_searchmanager.py	998	# Create a SearchInfo with an Azure Vision endpoint	COMMENT
MEDIUM	tests/test_searchmanager.py	1032	# Create a SearchManager with both search_images and embeddings	COMMENT
MEDIUM	tests/test_pdfparser.py	631	# Create a processor with an invalid strategy by patching the enum	COMMENT
MEDIUM	scripts/manageacl.py	231	# Create a session when paging through results to ensure consistency in multi-replica services	COMMENT
MEDIUM	scripts/auth_init.py	44	# Create a service principal	COMMENT

Hallucination Indicators11 hits · 110 pts

Severity	File	Line	Snippet	Context
CRITICAL	app/backend/error.py	4	from azure.core.exceptions import HttpResponseError	CODE
CRITICAL	app/backend/prepdocslib/pdfparser.py	19	from azure.core.exceptions import HttpResponseError	CODE
CRITICAL	app/backend/prepdocslib/blobmanager.py	10	from azure.core.exceptions import ResourceNotFoundError	CODE
CRITICAL	app/functions/document_extractor/function_app.py	15	from azure.core.exceptions import HttpResponseError	CODE
CRITICAL	tests/test_content_file.py	6	from azure.core.exceptions import ResourceNotFoundError	CODE
CRITICAL	tests/test_blob_manager.py	51	return azure.storage.blob.aio.BlobClient.from_blob_url(	CODE
CRITICAL	tests/test_blob_manager.py	100	return azure.storage.blob.aio.BlobClient.from_blob_url(	CODE
CRITICAL	tests/test_blob_manager.py	159	return azure.storage.blob.aio.BlobClient.from_blob_url(	CODE
CRITICAL	tests/test_blob_manager.py	223	return azure.storage.blob.aio.BlobClient.from_blob_url(	CODE
CRITICAL	tests/test_blob_manager.py	341	from azure.core.exceptions import ResourceNotFoundError	CODE
CRITICAL	tests/test_pdfparser.py	23	from azure.core.exceptions import HttpResponseError	CODE

Excessive Try-Catch Wrapping43 hits · 50 pts

Severity	File	Line	Snippet	Context
LOW	evals/evaltools/eval/evaluate.py	69	except Exception:	CODE
LOW	evals/evaltools/eval/evaluate.py	80	except Exception as e:	CODE
LOW	evals/evaltools/eval/evaluate.py	138	except Exception as e:	CODE
LOW	app/backend/app.py	207	except Exception as error:	CODE
LOW	app/backend/app.py	237	except Exception as error:	CODE
LOW	app/backend/app.py	269	except Exception as error:	CODE
LOW	app/backend/app.py	350	except Exception as e:	CODE
LOW	app/backend/app.py	370	except Exception as error:	CODE
LOW	app/backend/prepdocs.py	45	except Exception as e:	CODE
LOW	app/backend/prepdocs.py	351	except Exception as e:	CODE
LOW	app/backend/decorators.py	29	except Exception as error:	CODE
LOW	app/backend/approaches/chatreadretrieveread.py	111	except Exception:	CODE
LOW	app/backend/core/authentication.py	174	except Exception:	CODE
LOW	app/backend/core/authentication.py	282	except Exception as exc:	CODE
LOW	app/backend/prepdocslib/pdfparser.py	74	except Exception:	CODE
LOW	app/backend/prepdocslib/page.py	46	except Exception as exc: # pragma: no cover - defensive	CODE
LOW	app/backend/prepdocslib/page.py	54	except Exception:	CODE
LOW	app/backend/prepdocslib/blobmanager.py	312	except Exception as e:	CODE
LOW	app/backend/prepdocslib/figureprocessor.py	143	except Exception: # pragma: no cover - embedding failures shouldn't abort figure processing	CODE
LOW	app/backend/chat_history/cosmosdb.py	75	except Exception as error:	CODE
LOW	app/backend/chat_history/cosmosdb.py	128	except Exception as error:	CODE
LOW	app/backend/chat_history/cosmosdb.py	168	except Exception as error:	CODE
LOW	app/backend/chat_history/cosmosdb.py	201	except Exception as error:	CODE
LOW	app/functions/text_processor/function_app.py	160	except Exception as exc: # pragma: no cover - defensive logging	CODE
LOW	app/functions/text_processor/function_app.py	227	except Exception as exc:	CODE
LOW	app/functions/document_extractor/function_app.py	192	except Exception as e:	CODE
LOW	app/functions/document_extractor/function_app.py	205	except Exception as e:	CODE
LOW	app/functions/document_extractor/function_app.py	336	except Exception as e:	CODE
LOW	app/functions/figure_processor/function_app.py	173	except Exception as exc: # pragma: no cover - defensive	CODE
LOW	tests/e2e.py	109	except Exception as e:	CODE
MEDIUM	tests/e2e.py	110	print(f"Error in test_chat handler (defaults validation): {e}")	CODE
LOW	tests/e2e.py	264	except Exception as e:	CODE
MEDIUM	tests/e2e.py	265	print(f"Error in test_chat_customization handler: {e}")	CODE
LOW	tests/e2e.py	332	except Exception as e:	CODE
MEDIUM	tests/e2e.py	333	print(f"Error in handle_chat: {e}")	CODE
LOW⚡	tests/e2e.py	452	except Exception as e:	CODE
MEDIUM⚡	tests/e2e.py	453	print(f"Error in test_chat_followup_streaming handler: {e}")	CODE
LOW	tests/e2e.py	649	except Exception as e:	CODE
MEDIUM	tests/e2e.py	650	print(f"Error in test_chat_customization handler: {e}")	CODE
LOW⚡	tests/test_authenticationhelper.py	380	except Exception as e:	CODE
LOW⚡	tests/test_authenticationhelper.py	387	except Exception as e:	CODE
LOW	scripts/cosmosdb_migration.py	71	except Exception:	CODE
LOW	scripts/cosmosdb_migration.py	75	except Exception:	CODE

AI Slop Vocabulary14 hits · 31 pts

Severity	File	Line	Snippet	Context
MEDIUM	tests/mocks.py	263	"content": 'advanced data\nanalytics to present a clear picture of the complex interplay between	CODE
MEDIUM	tests/test-data/pages_with_figures.json	10	"text": "## Executive Summary\n\n. In this comprehensive report, Contoso Financial Analytics provides a\ndeep dive i	CODE
MEDIUM	tests/test-data/pages_with_figures.json	15	"text": "## Introduction to Financial Markets\n\n\n<figure><figcaption>Global Financial Market Distribution (2023)<b	CODE
MEDIUM	tests/test-data/pages_with_figures.json	30	"text": "### Commodity Market Fluctuations\n\n\n<figure><figcaption>Price Changes of Oil, Gold, and Wheat<br>This is	CODE
MEDIUM	tests/test-data/pages_with_figures.json	50	"text": "## Conclusions\n\n. In conclusion, this report has traversed the multifaceted landscape of\nfinancial marke	CODE
MEDIUM	tests/test-data/pages_with_figures.json	50	"text": "## Conclusions\n\n. In conclusion, this report has traversed the multifaceted landscape of\nfinancial marke	CODE
MEDIUM⚡	…napshots/test_app/test_chat_vision/client0/result.json	15	"Financial Market Analysis Report 2023.pdf#page=7: This section examines the correlations between stock	CODE
MEDIUM⚡	…napshots/test_app/test_chat_vision/client0/result.json	16	"Financial Market Analysis Report 2023.pdf#page=8: </figcaption></figure> Macroeconomic factors such a	CODE
MEDIUM⚡	…napshots/test_app/test_chat_vision/client0/result.json	17	"Financial Market Analysis Report 2023.pdf#page=2: advanced data analytics to present a clear picture of	CODE
MEDIUM	…napshots/test_app/test_chat_vision/client0/result.json	104	"content": "advanced data\nanalytics to present a clear picture of the complex interplay between	CODE
MEDIUM	…napshots/test_app/test_chat_vision/client0/result.json	139	"text": "Are interest rates high?\n\n\nSources:\n\nFinancial Market Analysis Report 2023	CODE
MEDIUM	…/pages_with_figures.json/split_pages_with_figures.json	7	"text": "## Executive Summary\n\n. In this comprehensive report, Contoso Financial Analytics provides a\ndeep dive i	CODE
MEDIUM	…/pages_with_figures.json/split_pages_with_figures.json	67	"text": "## Conclusions\n\n. In conclusion, this report has traversed the multifaceted landscape of\nfinancial marke	CODE
MEDIUM	…/pages_with_figures.json/split_pages_with_figures.json	67	"text": "## Conclusions\n\n. In conclusion, this report has traversed the multifaceted landscape of\nfinancial marke	CODE

Fake / Example Data29 hits · 30 pts

Severity	File	Line	Snippet	Context
LOW	app/frontend/src/locales/pl/translation.json	41	"placeholder": "Wpisz nowe pytanie (np. czy mój plan obejmuje coroczne badania wzroku?)"	CODE
LOW	app/frontend/src/locales/pl/translation.json	48	"placeholder": "Przykład: Czy mój plan obejmuje coroczne badania wzroku?"	CODE
LOW	app/frontend/src/locales/da/translation.json	41	"placeholder": "Skriv et nyt spørgsmål (f.eks. dækker min plan årlige øjenundersøgelser?)"	CODE
LOW	app/frontend/src/locales/da/translation.json	48	"placeholder": "Eksempel: Dækker min plan årlige øjenundersøgelser?"	CODE
LOW	app/frontend/src/locales/ja/translation.json	41	"placeholder": "新しい質問を入力してください (例：私の契約プランは年1回の眼科検診もカバーしていますか？)"	CODE
LOW	app/frontend/src/locales/ja/translation.json	48	"placeholder": "例：私の契約プランは年1回の眼科検診もカバーしていますか？"	CODE
LOW	app/frontend/src/locales/it/translation.json	41	"placeholder": "Digita una nuova domanda (es. il mio piano copre gli esami oculistici annuali?)"	CODE
LOW	app/frontend/src/locales/it/translation.json	48	"placeholder": "Esempio: Il mio piano copre gli esami oculistici annuali?"	CODE
LOW	app/frontend/src/locales/ptBR/translation.json	41	"placeholder": "Digite uma nova pergunta (por exemplo: Meu plano cobre exames oftalmológicos anuais?)"	CODE
LOW	app/frontend/src/locales/ptBR/translation.json	48	"placeholder": "Exemplo: Meu plano cobre exames oftalmológicos anuais?"	CODE
LOW	app/frontend/src/locales/nl/translation.json	41	"placeholder": "Typ een nieuwe vraag (bijv. dekt mijn pakket jaarlijkse oogonderzoeken?)"	CODE
LOW	app/frontend/src/locales/nl/translation.json	48	"placeholder": "Voorbeeld: dekt mijn pakket jaarlijkse oogonderzoeken?"	CODE
LOW	app/frontend/src/locales/fr/translation.json	41	"placeholder": "Tapez une nouvelle question (par exemple, mon plan couvre-t-il les examens oculaires annuels?)"	CODE
LOW	app/frontend/src/locales/fr/translation.json	48	"placeholder": "Exemple: Mon plan couvre-t-il les examens oculaires annuels?"	CODE
LOW	app/frontend/src/locales/es/translation.json	41	"placeholder": "Escribe una nueva pregunta (por ejemplo, ¿mi plan cubre exámenes anuales de la vista?)"	CODE
LOW	app/frontend/src/locales/es/translation.json	48	"placeholder": "Ejemplo: ¿Mi plan cubre exámenes anuales de la vista?"	CODE
LOW	app/frontend/src/locales/en/translation.json	41	"placeholder": "Type a new question (e.g. does my plan cover annual eye exams?)"	CODE
LOW	app/frontend/src/locales/en/translation.json	48	"placeholder": "Example: Does my plan cover annual eye exams?"	CODE
LOW	app/frontend/src/locales/tr/translation.json	41	"placeholder": "Yeni bir soru yazın (ör. planım yıllık göz muayenelerini kapsıyor mu?)"	CODE
LOW	app/frontend/src/locales/tr/translation.json	48	"placeholder": "Örnek: Planım yıllık göz muayenelerini kapsıyor mu?"	CODE
LOW	app/backend/prepdocslib/page.py	66	placeholder = data.get("placeholder")	CODE
LOW	app/backend/prepdocslib/cloudingestionstrategy.py	206	InputFieldMappingEntry(name="placeholder", source="/document/figures/*/placeholder"),	CODE
LOW	app/backend/prepdocslib/cloudingestionstrategy.py	236	InputFieldMappingEntry(name="placeholder", source="/document/figures/*/placeholder"),	CODE
LOW	app/functions/document_extractor/function_app.py	153	"placeholder": "<figure id=\"fig1\"></figure>"	STRING
LOW⚡	tests/test_prepdocs.py	165	mock_token_provider = AsyncMock(return_value="fake_token")	CODE
LOW	tests/test_servicesetup.py	147	"prepdocslib.servicesetup.get_bearer_token_provider", lambda args, *kwargs: lambda: "fake_token"	CODE
LOW⚡	tests/test_authenticationhelper.py	57	"name": "John Doe",	CODE
LOW	tests/test_chatapproach.py	631	({"access_token": "fake-token"}, True),	CODE
LOW⚡	tests/test_pdfparser.py	602	credential=AzureKeyCredential("fake_key"),	CODE

Deep Nesting24 hits · 23 pts

Severity	File	Line	Context
LOW	evals/evaltools/review/diff_markdown.py	14	CODE
LOW	evals/evaltools/review/utils.py	7	CODE
LOW	evals/evaltools/eval/evaluate.py	23	CODE
LOW	evals/evaltools/eval/evaluate.py	222	CODE
LOW	app/backend/approaches/approach.py	428	CODE
LOW	app/backend/approaches/approach.py	714	CODE
LOW	app/backend/core/authentication.py	118	CODE
LOW	app/backend/prepdocslib/pdfparser.py	65	CODE
LOW	app/backend/prepdocslib/textprocessor.py	14	CODE
LOW	app/backend/prepdocslib/embeddings.py	74	CODE
LOW	app/backend/prepdocslib/textsplitter.py	311	CODE
LOW	app/backend/prepdocslib/textsplitter.py	380	CODE
LOW	app/backend/prepdocslib/searchmanager.py	98	CODE
LOW	app/functions/document_extractor/function_app.py	267	CODE
LOW	tests/conftest.py	143	CODE
LOW	tests/conftest.py	215	CODE
LOW	tests/test_mediadescriber.py	21	CODE
LOW	tests/test_mediadescriber.py	45	CODE
LOW	tests/test_manageacl.py	367	CODE
LOW	tests/mocks.py	374	CODE
LOW	tests/mocks.py	386	CODE
LOW	scripts/manageacl.py	69	CODE
LOW	scripts/adlsgen2setup.py	58	CODE
LOW	scripts/manage_indexer.py	22	CODE

Over-Commented Block23 hits · 22 pts

Severity	File	Line	Snippet	Context
LOW	app/frontend/vite.config.ts	1	/// <reference types="node" />	COMMENT
LOW	app/backend/requirements.txt	1	# This file was autogenerated by uv via the following command:	COMMENT
LOW	app/backend/requirements.txt	21	async-timeout==5.0.1	COMMENT
LOW	app/backend/requirements.txt	41	# msrest	COMMENT
LOW	app/backend/requirements.txt	61	# -r requirements.in	COMMENT
LOW	app/backend/requirements.txt	81	click==8.4.2	COMMENT
LOW	app/backend/requirements.txt	101	# taskgroup	COMMENT
LOW	app/backend/requirements.txt	121	# via httpx	COMMENT
LOW	app/backend/requirements.txt	141	# azure-ai-documentintelligence	COMMENT
LOW	app/backend/requirements.txt	161	# flask	COMMENT
LOW	app/backend/requirements.txt	181	# via msgraph-sdk	COMMENT
LOW	app/backend/requirements.txt	201	multidict==6.7.0	COMMENT
LOW	app/backend/requirements.txt	221	# opentelemetry-instrumentation-fastapi	COMMENT
LOW	app/backend/requirements.txt	241	# opentelemetry-instrumentation-openai	COMMENT
LOW	app/backend/requirements.txt	261	opentelemetry-instrumentation-httpx==0.60b0	COMMENT
LOW	app/backend/requirements.txt	281	# azure-monitor-opentelemetry	COMMENT
LOW	app/backend/requirements.txt	301	# opentelemetry-instrumentation-wsgi	COMMENT
LOW	app/backend/requirements.txt	321	pillow==12.2.0	COMMENT
LOW	app/backend/requirements.txt	341	# -r requirements.in	COMMENT
LOW	app/backend/requirements.txt	361	# msrest	COMMENT
LOW	app/backend/requirements.txt	381	# via -r requirements.in	COMMENT
LOW	app/backend/requirements.txt	401	# azure-cosmos	COMMENT
LOW	app/backend/requirements.txt	421	# uvicorn	COMMENT

Redundant / Tautological Comments11 hits · 19 pts

Severity	File	Line	Snippet	Context
LOW	evals/evaltools/eval/evaluate_metrics/__init__.py	36	# Check if the metric name is already registered	COMMENT
LOW	.azdo/pipelines/azure-dev.yml	2	# Set this to the mainline branch you are using	COMMENT
LOW	app/backend/setup_cloud_ingestion.py	152	# Check if cloud ingestion is enabled	COMMENT
LOW	app/backend/core/authentication.py	98	# Set this to "true" if you are having issues on IE11 or Edge	COMMENT
LOW	app/backend/prepdocslib/csvparser.py	24	# Check if content is in bytes (binary file) and decode to string	COMMENT
LOW	app/functions/document_extractor/function_app.py	307	# Check if "other" has read permission - this means global access	COMMENT
LOW	tests/conftest.py	246	# Check if system prompt asks for followup questions	COMMENT
LOW⚡	scripts/load-balance-aca-setup.sh	19	# Check if resourceGroupName is empty	COMMENT
LOW⚡	scripts/load-balance-aca-setup.sh	25	# Check if containerAppName is empty	COMMENT
LOW⚡	scripts/load-balance-aca-setup.sh	34	# Check if fqdn is empty	COMMENT
LOW	.github/workflows/azure-dev.yml	7	# Set this to the mainline branch you are using	COMMENT

Docstring Block Structure2 hits · 10 pts

Severity	File	Line	Snippet	Context
HIGH	app/backend/prepdocslib/servicesetup.py	319	Select the appropriate file processor for a given filename. Args: file_name: Name of the file to process	STRING
HIGH	app/backend/prepdocslib/blobmanager.py	469	Downloads a blob from Azure Blob Storage. Args: blob_path: The path to the blob in the sto	STRING

Synthetic Comment Markers1 hit · 8 pts

Severity	File	Line	Snippet	Context
HIGH	data/Zava_Company_Overview.md	3	*Disclaimer: This content is generated by AI and may not accurately represent factual information about any real entity.	COMMENT

Verbosity Indicators3 hits · 7 pts

Severity	File	Line	Snippet	Context
LOW⚡	app/backend/prepdocslib/textprocessor.py	37	# Step 1: Combine text with figures on each page	COMMENT
LOW⚡	app/backend/prepdocslib/textprocessor.py	41	# Step 2: Split combined text into chunks	COMMENT
LOW⚡	app/backend/prepdocslib/textprocessor.py	45	# Step 3: Add images back to each section based on page number	COMMENT

Structural Annotation Overuse3 hits · 7 pts

Severity	File	Line	Snippet	Context
LOW⚡	app/backend/prepdocslib/textprocessor.py	37	# Step 1: Combine text with figures on each page	COMMENT
LOW⚡	app/backend/prepdocslib/textprocessor.py	41	# Step 2: Split combined text into chunks	COMMENT
LOW⚡	app/backend/prepdocslib/textprocessor.py	45	# Step 3: Add images back to each section based on page number	COMMENT

Cross-Language Confusion1 hit · 5 pts

Severity	File	Line	Snippet	Context
HIGH	tests/e2e.py	212	jsonl = '{"type": "response.context", "context": {"data_points": {"text": []}, "thoughts": []}, "session_state":	CODE

AI Structural Patterns4 hits · 4 pts

Severity	File	Line	Context
LOW	app/backend/prepdocs.py	62	CODE
LOW	app/backend/approaches/chatreadretrieveread.py	38	CODE
LOW	app/backend/prepdocslib/filestrategy.py	58	CODE
LOW	app/backend/prepdocslib/searchmanager.py	73	CODE

Modern Structural Boilerplate4 hits · 4 pts

Severity	File	Line	Snippet	Context
LOW	app/backend/approaches/approach.py	164	def update_token_usage(self, usage: CompletionUsage \| ResponseUsage) -> None:	CODE
LOW	app/functions/text_processor/function_app.py	32	logger = logging.getLogger(__name__)	CODE
LOW	app/functions/document_extractor/function_app.py	30	logger = logging.getLogger(__name__)	CODE
LOW	app/functions/figure_processor/function_app.py	36	logger = logging.getLogger(__name__)	CODE

Unused Imports4 hits · 4 pts

Severity	File	Line	Context
LOW	app/backend/prepdocslib/textprocessor.py	6	CODE
LOW	app/backend/prepdocslib/textprocessor.py	7	CODE
LOW	app/backend/prepdocslib/textprocessor.py	9	CODE
LOW	app/backend/prepdocslib/figureprocessor.py	17	CODE

Dead Code1 hit · 2 pts

Severity	File	Line	Snippet	Context
MEDIUM	tests/test_function_apps.py	278		CODE